37 KiB
37 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBufferAligned.kd | 0 | 0 | 0 | 68439 | 68439 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7fb15d804280 | 14801188122396 | 14801188147077 | 14801188386437 | 14801188495867 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 68439 | 68439 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7fb15d823f80 | 14801193175938 | 14801193191567 | 14801193205007 | 14801193222127 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7fb160719380 | 0x7fb15d823fc0 | 14801193227877 | 14801193270447 | 14801193362447 | 14801193364414 |
| 5 | 3 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 8 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7fb160719200 | 0x7fb15d824000 | 14801193386633 | 14801193396367 | 14801193576368 | 14801193578428 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7fb160719080 | 0x7fb15d824040 | 14801193592888 | 14801193601008 | 14801193783728 | 14801193785663 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7fb15df7df00 | 0x7fb15d824080 | 14801193799453 | 14801193807568 | 14801193900849 | 14801193902990 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7fb15df7dd80 | 0x7fb15d8240c0 | 14801193917800 | 14801193926129 | 14801194018289 | 14801194020177 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7fb15df7dc00 | 0x7fb15d824100 | 14801194046756 | 14801194057169 | 14801194149329 | 14801194151464 |
| 10 | 8 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 23 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7fb15df7da80 | 0x7fb15d824140 | 14801194167373 | 14801194176529 | 14801194356210 | 14801194357948 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7fb15df7d900 | 0x7fb15d824180 | 14801194374838 | 14801194383250 | 14801194563090 | 14801194565173 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7fb15df7d780 | 0x7fb15d8241c0 | 14801194582763 | 14801194602770 | 14801194696690 | 14801194698940 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7fb15df7d600 | 0x7fb15d824200 | 14801194713599 | 14801194721970 | 14801194815891 | 14801194817757 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7fb160719480 | 0x7fb15d824240 | 14801194837606 | 14801194847891 | 14801194942291 | 14801194944093 |
| 15 | 13 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 38 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7fb160719300 | 0x7fb15d824280 | 14801194966623 | 14801194976851 | 14801195157171 | 14801195159018 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7fb160719180 | 0x7fb15d8242c0 | 14801195179618 | 14801195189811 | 14801195369972 | 14801195371833 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7fb160719000 | 0x7fb15d824300 | 14801195392092 | 14801195402452 | 14801195496372 | 14801195498279 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7fb15df7de80 | 0x7fb15d824340 | 14801195516829 | 14801195525332 | 14801195618612 | 14801195620356 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7fb15df7dd00 | 0x7fb15d824380 | 14801195641466 | 14801195651892 | 14801195745013 | 14801195746873 |
| 20 | 18 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 53 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7fb15df7db80 | 0x7fb15d8243c0 | 14801195764213 | 14801195777973 | 14801195957333 | 14801195959488 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7fb15df7da00 | 0x7fb15d824400 | 14801195978127 | 14801195987093 | 14801196167254 | 14801196169102 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7fb15df7d880 | 0x7fb15d824440 | 14801196185602 | 14801196194454 | 14801196287734 | 14801196289689 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7fb15df7d700 | 0x7fb15d824480 | 14801196309079 | 14801196320054 | 14801196413174 | 14801196414996 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7fb160719580 | 0x7fb15d8244c0 | 14801196436086 | 14801196446614 | 14801196538454 | 14801196540283 |
| 25 | 23 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 68 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7fb160719400 | 0x7fb15d824500 | 14801196559423 | 14801196588215 | 14801196768375 | 14801196770257 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7fb160719280 | 0x7fb15d824540 | 14801196784097 | 14801196792535 | 14801196973975 | 14801196975922 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7fb160719100 | 0x7fb15d824580 | 14801196992092 | 14801197000215 | 14801197092536 | 14801197094309 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7fb15df7df80 | 0x7fb15d8245c0 | 14801197110319 | 14801197149016 | 14801197241656 | 14801197243605 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7fb15df7de00 | 0x7fb15d824600 | 14801197264665 | 14801197275256 | 14801197368696 | 14801197370022 |
| 30 | 28 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 83 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7fb15df7dc80 | 0x7fb15d824640 | 14801197385562 | 14801197394136 | 14801197573977 | 14801197575247 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7fb15df7db00 | 0x7fb15d824680 | 14801197590016 | 14801197597977 | 14801197778297 | 14801197779622 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7fb15df7d980 | 0x7fb15d8246c0 | 14801197794411 | 14801197802457 | 14801197895737 | 14801197897179 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7fb15df7d800 | 0x7fb15d824700 | 14801197912828 | 14801197920698 | 14801198014778 | 14801198016216 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7fb15df7d680 | 0x7fb15d824740 | 14801198037925 | 14801198047578 | 14801198140698 | 14801198142382 |
| 35 | 33 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 98 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7fb160719500 | 0x7fb15d824780 | 14801198157562 | 14801198165498 | 14801198345818 | 14801198347347 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7fb160719380 | 0x7fb15d8247c0 | 14801198361357 | 14801198369819 | 14801198549979 | 14801198551422 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7fb160719200 | 0x7fb15d824800 | 14801198565982 | 14801198573819 | 14801198668059 | 14801198669489 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7fb160719080 | 0x7fb15d824840 | 14801198683699 | 14801198691739 | 14801198786139 | 14801198787646 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7fb15df7df00 | 0x7fb15d824880 | 14801198808156 | 14801198818620 | 14801198911900 | 14801198913393 |
| 40 | 38 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 113 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7fb15df7dd80 | 0x7fb15d8248c0 | 14801198928243 | 14801198936220 | 14801199115100 | 14801199116608 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7fb15df7dc00 | 0x7fb15d824900 | 14801199130707 | 14801199138460 | 14801199319101 | 14801199320703 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7fb15df7da80 | 0x7fb15d824940 | 14801199335292 | 14801199344061 | 14801199437661 | 14801199439060 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7fb15df7d900 | 0x7fb15d824980 | 14801199452759 | 14801199460701 | 14801199555741 | 14801199557227 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7fb15df7d780 | 0x7fb15d8249c0 | 14801199576806 | 14801199587581 | 14801199681501 | 14801199683033 |
| 45 | 43 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 128 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7fb15df7d600 | 0x7fb15d824a00 | 14801199697353 | 14801199705182 | 14801199885022 | 14801199886528 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7fb160719480 | 0x7fb15d824a40 | 14801199900558 | 14801199908382 | 14801200088862 | 14801200090423 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7fb160719300 | 0x7fb15d824a80 | 14801200104853 | 14801200112862 | 14801200205503 | 14801200206840 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7fb160719180 | 0x7fb15d824ac0 | 14801200220720 | 14801200229503 | 14801200323103 | 14801200324547 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7fb160719000 | 0x7fb15d824b00 | 14801200345397 | 14801200355903 | 14801200447743 | 14801200449084 |
| 50 | 48 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 143 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7fb15df7de80 | 0x7fb15d824b40 | 14801200467134 | 14801200475263 | 14801200653984 | 14801200655399 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7fb15df7dd00 | 0x7fb15d824b80 | 14801200670538 | 14801200678464 | 14801200859104 | 14801200860444 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7fb15df7db80 | 0x7fb15d824bc0 | 14801200874733 | 14801200882464 | 14801200976064 | 14801200977431 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7fb15df7da00 | 0x7fb15d824c00 | 14801200991640 | 14801200999744 | 14801201095585 | 14801201096858 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7fb15df7d880 | 0x7fb15d824c40 | 14801201116277 | 14801201127745 | 14801201221185 | 14801201222474 |
| 55 | 53 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 158 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7fb15df7d700 | 0x7fb15d824c80 | 14801201236714 | 14801201245345 | 14801201424385 | 14801201425619 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7fb160719580 | 0x7fb15d824cc0 | 14801201439159 | 14801201447745 | 14801201627586 | 14801201628974 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7fb160719400 | 0x7fb15d824d00 | 14801201642764 | 14801201650626 | 14801201745506 | 14801201746851 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7fb160719280 | 0x7fb15d824d40 | 14801201761701 | 14801201769666 | 14801201868866 | 14801201870268 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7fb160719100 | 0x7fb15d824d80 | 14801201890437 | 14801201901346 | 14801201994307 | 14801201995575 |
| 60 | 58 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 173 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7fb15df7df80 | 0x7fb15d824dc0 | 14801202011234 | 14801202019107 | 14801202197187 | 14801202198660 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7fb15df7de00 | 0x7fb15d824e00 | 14801202213949 | 14801202221667 | 14801202400548 | 14801202402164 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7fb15df7dc80 | 0x7fb15d824e40 | 14801202415844 | 14801202423588 | 14801202517988 | 14801202519422 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7fb15df7db00 | 0x7fb15d824e80 | 14801202533911 | 14801202541988 | 14801202647588 | 14801202649078 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7fb15df7d980 | 0x7fb15d824ec0 | 14801202668878 | 14801202679588 | 14801202772228 | 14801202773625 |
| 65 | 63 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 188 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7fb15df7d800 | 0x7fb15d824f00 | 14801202787815 | 14801202795588 | 14801202975109 | 14801202976670 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7fb15df7d680 | 0x7fb15d824f40 | 14801202992000 | 14801203000229 | 14801203179109 | 14801203180615 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7fb160719500 | 0x7fb15d824f80 | 14801203193914 | 14801203201509 | 14801203294630 | 14801203296162 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7fb160719380 | 0x7fb15d824fc0 | 14801203309651 | 14801203317670 | 14801203424870 | 14801203426159 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7fb160719200 | 0x7fb15d825000 | 14801203445378 | 14801203457510 | 14801203552070 | 14801203553585 |
| 70 | 68 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 203 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7fb160719080 | 0x7fb15d825040 | 14801203567075 | 14801203574950 | 14801203755431 | 14801203756880 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7fb15df7df00 | 0x7fb15d825080 | 14801203771550 | 14801203779271 | 14801203960391 | 14801203961815 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7fb15df7dd80 | 0x7fb15d8250c0 | 14801203975685 | 14801203983591 | 14801204078951 | 14801204080372 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7fb15df7dc00 | 0x7fb15d825100 | 14801204094642 | 14801204102631 | 14801204217352 | 14801204218598 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7fb15df7da80 | 0x7fb15d825140 | 14801204252048 | 14801204261832 | 14801204356392 | 14801204357705 |
| 75 | 73 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 218 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7fb15df7d900 | 0x7fb15d825180 | 14801204372315 | 14801204380072 | 14801204561192 | 14801204562570 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7fb15df7d780 | 0x7fb15d8251c0 | 14801204576999 | 14801204584872 | 14801204765993 | 14801204767425 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7fb15df7d600 | 0x7fb15d825200 | 14801204780834 | 14801204788553 | 14801204883913 | 14801204885242 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7fb160719480 | 0x7fb15d825240 | 14801204899881 | 14801204908233 | 14801205029033 | 14801205030328 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7fb160719300 | 0x7fb15d825280 | 14801205049577 | 14801205061513 | 14801205155914 | 14801205157495 |
| 80 | 78 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 233 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7fb160719180 | 0x7fb15d8252c0 | 14801205174254 | 14801205182154 | 14801205361674 | 14801205363049 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7fb160719000 | 0x7fb15d825300 | 14801205378779 | 14801205386794 | 14801205567275 | 14801205568704 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7fb15df7de80 | 0x7fb15d825340 | 14801205583474 | 14801205591435 | 14801205687435 | 14801205688721 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7fb15df7dd00 | 0x7fb15d825380 | 14801205702291 | 14801205710795 | 14801205838155 | 14801205839477 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7fb15df7db80 | 0x7fb15d8253c0 | 14801205860107 | 14801205870795 | 14801205965355 | 14801205966754 |
| 85 | 83 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 248 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7fb15df7da00 | 0x7fb15d825400 | 14801205981004 | 14801205989036 | 14801206169516 | 14801206171189 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7fb15df7d880 | 0x7fb15d825440 | 14801206185459 | 14801206193196 | 14801206372556 | 14801206374094 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7fb15df7d700 | 0x7fb15d825480 | 14801206388713 | 14801206396556 | 14801206490957 | 14801206492451 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7fb160719580 | 0x7fb15d8254c0 | 14801206507260 | 14801206515277 | 14801206645837 | 14801206647327 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7fb160719400 | 0x7fb15d825500 | 14801206666826 | 14801206677677 | 14801206770797 | 14801206772464 |
| 90 | 88 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 263 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7fb160719280 | 0x7fb15d825540 | 14801206787373 | 14801206795437 | 14801206974638 | 14801206976149 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7fb160719100 | 0x7fb15d825580 | 14801206990388 | 14801206998158 | 14801207178958 | 14801207180493 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7fb15df7df80 | 0x7fb15d8255c0 | 14801207194883 | 14801207202638 | 14801207298158 | 14801207299640 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7fb15df7de00 | 0x7fb15d825600 | 14801207314550 | 14801207322799 | 14801207461199 | 14801207462616 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7fb15df7dc80 | 0x7fb15d825640 | 14801207482926 | 14801207493679 | 14801207588079 | 14801207589583 |
| 95 | 93 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 278 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7fb15df7db00 | 0x7fb15d825680 | 14801207605053 | 14801207612879 | 14801207791920 | 14801207793498 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7fb15df7d980 | 0x7fb15d8256c0 | 14801207807617 | 14801207816080 | 14801207997840 | 14801207999393 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7fb15df7d800 | 0x7fb15d825700 | 14801208013692 | 14801208022320 | 14801208118960 | 14801208120280 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7fb15df7d680 | 0x7fb15d825740 | 14801208135729 | 14801208143440 | 14801208289201 | 14801208290515 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7fb160719500 | 0x7fb15d825780 | 14801208311895 | 14801208322161 | 14801208417681 | 14801208419062 |
| 100 | 98 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 293 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7fb160719380 | 0x7fb15d8257c0 | 14801208433332 | 14801208441521 | 14801208620881 | 14801208622227 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7fb160719200 | 0x7fb15d825800 | 14801208636446 | 14801208644561 | 14801208824562 | 14801208825842 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7fb160719080 | 0x7fb15d825840 | 14801208839751 | 14801208848242 | 14801208948882 | 14801208950329 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7fb15df7df00 | 0x7fb15d825880 | 14801208966788 | 14801208974802 | 14801209130323 | 14801209131764 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7fb15df7dd80 | 0x7fb15d8258c0 | 14801209153433 | 14801209164083 | 14801209258803 | 14801209260151 |
| 105 | 103 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 308 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7fb15df7dc00 | 0x7fb15d825900 | 14801209276860 | 14801209284403 | 14801209463603 | 14801209464955 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7fb15df7da80 | 0x7fb15d825940 | 14801209481765 | 14801209490323 | 14801209671764 | 14801209673180 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7fb15df7d900 | 0x7fb15d825980 | 14801209687940 | 14801209695924 | 14801209804404 | 14801209805807 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7fb15df7d780 | 0x7fb15d8259c0 | 14801209822266 | 14801209830324 | 14801210000724 | 14801210002122 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7fb15df7d600 | 0x7fb15d825a00 | 14801210022651 | 14801210033365 | 14801210129365 | 14801210130959 |
| 110 | 108 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 323 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7fb160719480 | 0x7fb15d825a40 | 14801210145658 | 14801210153205 | 14801210333845 | 14801210335343 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7fb160719300 | 0x7fb15d825a80 | 14801210349203 | 14801210357045 | 14801210538966 | 14801210540518 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7fb160719180 | 0x7fb15d825ac0 | 14801210554008 | 14801210561846 | 14801210672086 | 14801210673615 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7fb160719000 | 0x7fb15d825b00 | 14801210688074 | 14801210695766 | 14801210877046 | 14801210878560 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7fb15df7de80 | 0x7fb15d825b40 | 14801210900139 | 14801210909847 | 14801211011447 | 14801211012896 |
| 115 | 113 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 338 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7fb15df7dd00 | 0x7fb15d825b80 | 14801211027376 | 14801211035447 | 14801211218967 | 14801211220541 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7fb15df7db80 | 0x7fb15d825bc0 | 14801211234741 | 14801211242487 | 14801211430008 | 14801211431476 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7fb15df7da00 | 0x7fb15d825c00 | 14801211445325 | 14801211453368 | 14801211576088 | 14801211577652 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7fb15df7d880 | 0x7fb15d825c40 | 14801211591792 | 14801211599608 | 14801211806489 | 14801211829226 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7fb15df7d700 | 0x7fb15d825c80 | 14801211844055 | 14801211855129 | 14801211966009 | 14801211967352 |
| 120 | 118 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 353 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7fb160719580 | 0x7fb15d825cc0 | 14801211983142 | 14801211991929 | 14801212174969 | 14801212176747 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7fb160719400 | 0x7fb15d825d00 | 14801212189466 | 14801212197849 | 14801212383770 | 14801212385101 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7fb160719280 | 0x7fb15d825d40 | 14801212400461 | 14801212408730 | 14801212543130 | 14801212544497 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7fb160719100 | 0x7fb15d825d80 | 14801212558197 | 14801212566970 | 14801212799611 | 14801212821240 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7fb15df7df80 | 0x7fb15d825dc0 | 14801212836030 | 14801212846971 | 14801212973371 | 14801212974837 |
| 125 | 123 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 368 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7fb15df7de00 | 0x7fb15d825e00 | 14801212990156 | 14801212998011 | 14801213191132 | 14801213192531 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7fb15df7dc80 | 0x7fb15d825e40 | 14801213206411 | 14801213215132 | 14801213408892 | 14801213410305 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7fb15df7db00 | 0x7fb15d825e80 | 14801213424215 | 14801213432572 | 14801213592572 | 14801213593891 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7fb15df7d980 | 0x7fb15d825ec0 | 14801213608680 | 14801213617053 | 14801213900573 | 14801213920563 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7fb15df7d800 | 0x7fb15d825f00 | 14801213936282 | 14801213946813 | 14801214096414 | 14801214097808 |
| 130 | 128 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 383 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7fb15df7d680 | 0x7fb15d825f40 | 14801214114108 | 14801214122014 | 14801214330494 | 14801214376971 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7fb160719500 | 0x7fb15d825f80 | 14801214384911 | 14801214394974 | 14801214601375 | 14801214644734 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7fb160719380 | 0x7fb15d825fc0 | 14801214652774 | 14801214663135 | 14801214849055 | 14801214850389 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7fb160719200 | 0x7fb15d826000 | 14801214864959 | 14801214872895 | 14801215207616 | 14801215248129 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7fb160719080 | 0x7fb15d826040 | 14801215262759 | 14801215273536 | 14801215441697 | 14801215443094 |
| 135 | 133 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 398 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7fb15df7df00 | 0x7fb15d826080 | 14801215457854 | 14801215465697 | 14801215693697 | 14801215733687 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7fb15df7dd80 | 0x7fb15d8260c0 | 14801215741696 | 14801215751937 | 14801215982178 | 14801215998100 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7fb15df7dc00 | 0x7fb15d826100 | 14801216006830 | 14801216017058 | 14801216228418 | 14801216244144 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7fb15df7da80 | 0x7fb15d826140 | 14801216252883 | 14801216261858 | 14801216647779 | 14801216663453 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7fb15df7d900 | 0x7fb15d826180 | 14801216678563 | 14801216689699 | 14801216875940 | 14801216877328 |
| 140 | 138 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 413 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7fb15df7d780 | 0x7fb15d8261c0 | 14801216894037 | 14801216901860 | 14801217151140 | 14801217166770 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7fb15df7d600 | 0x7fb15d826200 | 14801217174320 | 14801217184741 | 14801217432901 | 14801217449203 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7fb160719480 | 0x7fb15d826240 | 14801217458603 | 14801217469221 | 14801217706182 | 14801217721856 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7fb160719300 | 0x7fb15d826280 | 14801217729526 | 14801217739782 | 14801218193063 | 14801218235923 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7fb160719180 | 0x7fb15d8262c0 | 14801218251853 | 14801218262343 | 14801218487623 | 14801218530846 |
| 145 | 143 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 428 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7fb160719000 | 0x7fb15d826300 | 14801218539435 | 14801218549864 | 14801218848264 | 14801218891707 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7fb15df7de80 | 0x7fb15d826340 | 14801218900626 | 14801218910184 | 14801219208425 | 14801219251397 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7fb15df7dd00 | 0x7fb15d826380 | 14801219262437 | 14801219272905 | 14801219569386 | 14801219609028 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7fb15df7db80 | 0x7fb15d8263c0 | 14801219620608 | 14801219631306 | 14801220189867 | 14801220210133 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7fb15df7da00 | 0x7fb15d826400 | 14801220225473 | 14801220236107 | 14801220500268 | 14801220519285 |
| 150 | 148 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 443 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7fb15df7d880 | 0x7fb15d826440 | 14801220527335 | 14801220537708 | 14801220889549 | 14801220907815 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7fb15df7d700 | 0x7fb15d826480 | 14801220916875 | 14801220927789 | 14801221278350 | 14801221297426 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7fb160719580 | 0x7fb15d8264c0 | 14801221307725 | 14801221318030 | 14801221665071 | 14801221681136 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7fb160719400 | 0x7fb15d826500 | 14801221690236 | 14801221700271 | 14801222362832 | 14801222414437 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7fb160719280 | 0x7fb15d826540 | 14801222432237 | 14801222442032 | 14801222889873 | 14801222933244 |
| 155 | 153 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 458 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7fb160719100 | 0x7fb15d826580 | 14801222942524 | 14801222952753 | 14801223418834 | 14801223466651 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7fb15df7df80 | 0x7fb15d8265c0 | 14801223477340 | 14801223487155 | 14801223947796 | 14801224043366 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7fb15df7de00 | 0x7fb15d826600 | 14801224054266 | 14801224062996 | 14801224515797 | 14801224539343 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7fb15df7dc80 | 0x7fb15d826640 | 14801224548073 | 14801224557877 | 14801225427479 | 14801225450680 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7fb15df7db00 | 0x7fb15d826680 | 14801225466250 | 14801225477079 | 14801226331161 | 14801226379887 |
| 160 | 158 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 473 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7fb15df7d980 | 0x7fb15d8266c0 | 14801226390197 | 14801226400121 | 14801227284923 | 14801227331833 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7fb15df7d800 | 0x7fb15d826700 | 14801227341422 | 14801227350843 | 14801228229885 | 14801228274759 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7fb15df7d680 | 0x7fb15d826740 | 14801228285348 | 14801228293885 | 14801229153887 | 14801229198725 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7fb160719500 | 0x7fb15d826780 | 14801229206605 | 14801229224607 | 14801230924131 | 14801230997300 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7fb160719380 | 0x7fb15d8267c0 | 14801231014369 | 14801231025091 | 14801232690535 | 14801232758195 |
| 165 | 163 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 488 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7fb160719200 | 0x7fb15d826800 | 14801232766645 | 14801232776775 | 14801234502859 | 14801234570769 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7fb160719080 | 0x7fb15d826840 | 14801234579449 | 14801234589579 | 14801236304463 | 14801236348224 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7fb15df7df00 | 0x7fb15d826880 | 14801236357254 | 14801236367503 | 14801238042547 | 14801238394592 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 68439 | 68439 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7fb15df7dd80 | 0x7fb15d8268c0 | 14801238412042 | 14801238422868 | 14801241780475 | 14801241903603 |